© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60831
    Prev
    Next
    INDEX
    Explanations

    jumping or words like jump

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -1.80
    Você
    -1.63
    我们在
    -1.59
    雛
    -1.58
    .”
    -1.56
    𝑀
    -1.52
    骤
    -1.49
     Präsentation
    -1.48
    เรา
    -1.48
     Miß
    -1.47
    POSITIVE LOGITS
    籥
    1.85
    jump
    1.80
     jumped
    1.61
    泚
    1.58
     protestas
    1.55
     are
    1.53
     jump
    1.51
     jumps
    1.49
    アレル
    1.45
     JUMP
    1.41
    Activations Density 0.013%

    No Known Activations